CVE-2026-54233 — vLLM: OOM Denial of Service via Audio Decompression Bomb
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, vLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not deco…
Published: 2026-06-22 · CVSS: 6.5 · CVSS 3.1
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, vLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not decoded PCM output. A 25MB OPUS file expands to ~14.9GB of float32 PCM at decode time. This vulnerability is fixed in 0.23.1rc0.
Source: CVE Program · Revision 8b16575c39f1e1810c5e863010da073d2d3285e7